Scene enhancements in off-center peripheral regions for nonlinear lens geometries
AssigneeFotoNation Limited
InventorsPeter Corcoran, Petronel Bigioi, Piotr Stec
Life of this patent
Estimating the term…
Abstract
A technique of enhancing a scene containing one or more off-center peripheral regions within an initial distorted image captured with a large field of view includes determining and extracting an off-center region of interest (hereinafter “ROI”) within the image. Geometric correction is applied to reconstruct the off-center ROI into a rectangular frame of reference as a reconstructed ROI. A quality of reconstructed pixels is determined within the reconstructed ROI. Image analysis is selectively applied to the reconstructed ROI based on the quality of the reconstructed pixels.
Claims18
Within an image acquisition system comprising a non-linear, wide-angled lens and an imaging sensor, a method of enhancing a scene containing one or more off-center peripheral regions, the method comprising:
- acquiring, using a nonlinear, wide-angled lens and an imaging sensor, an initial distorted image with a large field of view;
- generating a reconstructed image from the initial distorted image, wherein the reconstructed image includes a plurality of reconstructed regions;
- wherein each reconstructed region of the plurality of reconstructed regions has a corresponding region quality;
- wherein the region quality of each reconstructed region of the plurality of reconstructed regions is based on reconstruction factors of reconstructed pixels within the reconstructed region;
- wherein the reconstruction factor for a reconstructed pixel reflects how much data, from the image sensor, the reconstructed pixel was extrapolated based on;
- based on the region qualities of said plurality of reconstructed regions, determining one or more reduced quality regions within said plurality of reconstructed regions;
- determining whether any undetected faces below a size threshold are likely to exist in the one or more reduced quality regions;
- and
- in response to determining that any undetected faces below the size threshold are likely to exist in the one or more reduced quality regions, performing the steps of:
- generating one or more enhanced regions of interest that correspond to the one or more reduced quality regions;
- and
- applying face detecting or tracking, or both, to the one or more enhanced regions of interest to confirm presence of a face below the size threshold.
A digital image acquisition device, comprising:
- a non-linear, wide-angled lens and an imaging sensor configured to capture digital images of scenes containing one or more off-center peripheral regions, including an initial distorted image with a large field of view;
- a processor;
- a memory having code embedded therein for programming the processor to perform a method of enhancing a scene containing one or more off-center peripheral regions, wherein the method comprises:
- generating a reconstructed image from the initial distorted image, wherein the reconstructed image includes a plurality of reconstructed regions;
- wherein each reconstructed region of the plurality of reconstructed regions has a corresponding region quality;
- wherein the region quality of each reconstructed region of the plurality of reconstructed regions is based on reconstruction factors of reconstructed pixels within the reconstructed region;
- wherein the reconstruction factor for a reconstructed pixel reflects how much data, from the image sensor, the reconstructed pixel was extrapolated based on;
- based on the region qualities of said plurality of reconstructed regions, determining one or more reduced quality regions within said plurality of reconstructed regions;
- determining whether any undetected faces below a size threshold are likely to exist in the one or more reduced quality regions;
- and
- in response to determining that any undetected faces below the size threshold are likely to exist in the one or more reduced quality regions, performing the steps of:
- generating one or more enhanced regions of interest that correspond to the one or more reduced quality regions;
- and
- applying face detecting or tracking, or both, to the one or more enhanced regions of interest to confirm presence of a face below the size threshold.
One or more non-transitory, processor-readable storage media having code embedded therein for programming a processor to perform a method of enhancing a scene captured with a non-linear, wide-angled lens and containing one or more off-center peripheral regions, wherein the method comprises:
- acquiring using a nonlinear, wide-angled lens and an imaging sensor, an initial distorted image with a large field of view;
- generating a reconstructed image from the initial distorted image, wherein the reconstructed image includes a plurality of reconstructed regions;
- wherein each reconstructed region of the plurality of reconstructed regions has a corresponding region quality;
- wherein the region quality of each reconstructed region of the plurality of reconstructed regions is based on reconstruction factors of reconstructed pixels within the reconstructed region;
- wherein the reconstruction factor for a reconstructed pixel reflects how much data, from the image sensor, the reconstructed pixel was extrapolated based on;
- based on the region qualities of said plurality of reconstructed regions, determining one or more reduced quality regions within said plurality of reconstructed regions;
- determining whether any undetected faces below a size threshold are likely to exist in the one or more reduced quality regions;
- and
- in response to determining that any undetected faces below the size threshold are likely to exist in the one or more reduced quality regions, performing the steps of:
- generating one or more enhanced regions of interest that correspond to the one or more reduced quality regions;
- and
- applying face detecting or tracking, or both, to the one or more enhanced regions of interest to confirm presence of a face below the size threshold.
Dependencies are inferred from the claim text.